CN106093652A - A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function - Google Patents

A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function Download PDF

Info

Publication number
CN106093652A
CN106093652A CN201610530542.9A CN201610530542A CN106093652A CN 106093652 A CN106093652 A CN 106093652A CN 201610530542 A CN201610530542 A CN 201610530542A CN 106093652 A CN106093652 A CN 106093652A
Authority
CN
China
Prior art keywords
load
electric
electric equipment
monitoring
type
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201610530542.9A
Other languages
Chinese (zh)
Other versions
CN106093652B (en
Inventor
栾文鹏
刘博�
余贻鑫
刘卫涛
刘中胜
刘浩
杨静
马骁
杜伟强
蒋仲明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
TIANJIN TRANSENERGY TECHNOLOGIES Co Ltd
Original Assignee
TIANJIN TRANSENERGY TECHNOLOGIES Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by TIANJIN TRANSENERGY TECHNOLOGIES Co Ltd filed Critical TIANJIN TRANSENERGY TECHNOLOGIES Co Ltd
Priority to CN201610530542.9A priority Critical patent/CN106093652B/en
Publication of CN106093652A publication Critical patent/CN106093652A/en
Application granted granted Critical
Publication of CN106093652B publication Critical patent/CN106093652B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere

Abstract

nullThe invention provides a kind of non-intrusive electrical load monitoring System and method for possessing self-learning function,On the basis of the non-intrusive electrical load monitoring technology system not possessing the automatic maintenance function in electric equipment load profile storehouse,Add and do not model electric equipment load characteristic automatic generation function,Can automatically detect the internal existence of electric load monitored does not models electric equipment,And automatically extract its load characteristic parameter,Final in order to update the electric equipment load profile storehouse of non-intrusive electrical load monitoring technology system,Thus be no longer necessary to technical staff and safeguard by the way of artificial return visit user and update electric equipment load profile storehouse,Can by the electric equipment load profile storehouse that upgrades in time ensure the Monitoring Performance of system introduce inside electric load do not model electric equipment time unaffected,The operational efficiency of non-intrusive electrical load monitoring technology system can be improved again by saving human cost.

Description

A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function
Technical field
The invention belongs to electric load monitoring field, especially relate to a kind of non-intrusion type electric power possessing self-learning function Load monitor system and method.
Background technology
Non-intrusive electrical load monitoring (Non-intrusive Load Monitoring, NILM) is a kind of novelty Electric load electricity consumption details monitoring technology, specifically by electricity consumption port, (such as a family resident or building building, an industry is female Line or factory floor, so that a micro-capacitance sensor) sensor is installed at total mouth, by analysis load in the measurement of total mouth Information (terminal voltage, total current) is carried out the power information of every kind of electric equipment within total load and is realized the tracking prison that (being close to) is real-time Survey, obtain subitem power information, include but not limited to the duty of all electric equipments, electric power and total electricity consumption etc. Power information.The current intelligent electric meter of this technological break-through can only carry out the present situation of electricity consumption total Amount Monitoring to electric load, will use Electric information monitoring gos deep into, refine to inside electric load.For obtaining electricity consumption detailed information, with traditional intrusive mood monitoring Technology is compared, and non-intrusive electrical load monitoring technology has incomparable investment, disposes and operation advantage.
Up to the present, non-intrusive electrical load monitoring technology mainly includes two big classes: monitoring based on steady-state analysis Technology and monitoring technology based on transient event.For load monitoring technology based on steady-state analysis, when electric equipment is in During stable state, it is possible to use non-intrusive electrical load decomposition method based on stable state frequency analysis, it is achieved electric load is sampled, divided The series of algorithms such as solution, superposition, thus obtain the electric load power information of primary electricity using device.
Setting up load profile storehouse is the basis realizing NILM.In many about in the research of NILM, such as " south is electric Network technology " document of entitled " non-intrusion type residential power load monitoring and the decomposition technique " disclosed in periodical, and Patent No. CN200810053059.1 entitled " method for real time sorting non-intrusion type electric load " all refer to set up electric equipment load The problem of property data base.Limited by engineering physical condition, set up in a short time and safeguard that one exists about in modern society " overall " data bases of load characteristic of all electric equipments be relatively difficult, but, based on special to electric equipment electricity consumption Property general character understanding, promote the initial stage in NILM technical applicationization, set up and safeguard for each concrete monitoring (or application) scene " local " load profile storehouse have more practical significance and operability.
The foundation in load profile storehouse and maintenance relate generally to two work: (1) disposes the initial stage at NILM technological system, Setting up or default load property data base, (2), when user's later stage increases or changes electric equipment, safeguard and update load characteristic Data base.Currently for the former, usually at the beginning of technical staff to time on-the-spot directly to each user existing electric equipment amount of carrying out Survey and gather its electricity consumption characteristic parameter with default electric equipment load profile storehouse;So, dispose in fact at NILM technological system Shi Hou, for the latter, is the most manually paid a return visit by technical staff and safeguards that electric equipment load profile storehouse is apparently not one Individual good selection, reason is that this can not accomplish that load profile storehouse updates and safeguards timely, and this can make the prison of system Survey accuracy affected by newly-increased electric equipment and declined, although improve return visit frequency can ensure to a certain extent renewal and Shi Xing, but due to the newly-increased of consumer electronics equipment or change and infrequently, and do not have rule to follow, high-frequency artificial return visit It is actually poor efficiency.
Summary of the invention
The problems referred to above existed in view of this area, the present invention proposes a kind of non-intrusion type electric power possessing self-learning function Load monitor system and method, it is intended to solve tradition non-intrusive electrical load monitoring technology system and bear because not possessing electric equipment The automatic maintenance function of lotus property data base and make it update and safeguard not in time, ultimately result in monitoring result accuracy reduce, with And high cost, inefficient artificial regeneration and maintenance scheme make the poor practicability of non-intrusive electrical load monitoring technology, The problem hindering its Technique Popularizing eventually.
In invention, tradition non-intrusive electrical load monitoring technology system refers to do not possess electric equipment load characteristic The system of the automatic maintenance function of data base, it is known that electric equipment refers to that being included it in electric equipment load profile storehouse bears The electric equipment of lotus characteristic, then, along with the renewal in electric equipment load profile storehouse, it is known that the quantity of electric equipment With or type can change, do not model electric equipment and refer to not comprise its load in electric equipment load profile storehouse The electric equipment of characteristic, such as, at the beginning of non-intrusive electrical load monitoring technology system deployment, inside electric load also Do not exist, the new electric equipment that user increases later.In order to solve above-mentioned technical problem, the technical solution used in the present invention Be: a kind of non-intrusive electrical load monitoring system possessing self-learning function, including electric load electricity consumption data acquisition module, The internal electric equipment electricity consumption state monitoring module of electric load electrical feature acquisition module, electric load, electric equipment load are special Levy DBM, external interactive function module, also include not modeling electric equipment type load characteristic generation module;
Described electric load electricity consumption data acquisition module, for gathering the terminal voltage of electric load power supply porch And total current;
Described electric load electrical feature acquisition module, the electricity that electric load electricity consumption data collecting module collected is arrived The data such as pressure, current data are filtered, noise reduction, smooth process, and then obtain the internal electric equipment electricity condition of electric load Electric load feature needed for monitoring modular;
The internal electric equipment electricity consumption state monitoring module of described electric load is for obtaining according to electric load electrical feature The electric load feature that delivery block provides, uses rational non-intrusive electrical load monitoring solving model and method for solving, really That determines the internal every kind of electric equipment type of electric load uses electricity condition, including duty and/or the electric power of electric equipment Two aspect contents;
Described electric equipment load profile library module is used for storing and managing the load profile of electric equipment, The access in electric equipment load profile storehouse is provided to connect including to the internal electric equipment electricity consumption state monitoring module of electric load Mouthful, and receive and store the load not modeling electric equipment that the offer of electric equipment type load characteristic generation module is not provided Characteristic;
Described external interactive function module is used for realizing other functions in non-intrusive electrical load monitoring technology system Data message interactive function necessary between module and the external world, include but not limited to monitoring result show, control command input and Output and System Reports output;
Described does not models electric equipment type load characteristic generation module for according to electric equipment electricity consumption status monitoring As a result, that automatically detects the internal existence of electric load monitored does not models electric equipment, automatically obtains its load characteristic parameter sample This, further, described does not models electric equipment type load characteristic generation module, the electric equipment used according to system The needs of electricity consumption state monitoring method, export the load profile not modeling electric equipment to electric equipment load characteristic number Preserve according to library module and by described electric equipment load profile library module.
Further, described electric load electricity consumption data acquisition module, gather the strong voltage at power import, big electric current Analogue signal, and it is converted into light current pressure and/or the small area analysis simulation that electric load electrical feature acquisition module can process Signal, then by acquired light current pressure and/or small area analysis analog signal digital, obtains mould for electric load electrical feature Block extracts required electric power load electrical feature.
The present invention also provides for a kind of non-intrusive electrical load monitoring method possessing self-learning function, is applied to above institute In a kind of non-intrusive electrical load monitoring system possessing self-learning function stated, comprise the following steps:
Step 201: parameter initialization, presets electric equipment load profile storehouse;
Step 202: gather electric load electricity consumption data, extracts the electric load characteristic of current time;
Step 203: utilize effective non-intrusive electrical load monitoring technology to carry out inside the electric load of current time Electric equipment electricity consumption status monitoring;
Step 204: according to monitoring result, it is judged that and record whether to exist inside current time electric load and do not model electrical equipment Device type, if adjacent two judge in the moment, with the presence of and the electric load in only one of which moment is internal does not models Electric equipment type;Then perform step 205;Otherwise go to step 208;
Step 205: do not model electric equipment type according to current to previous whether exist about electric load inside Judge the electric load characteristic in moment, extract the load characteristic parameter sample not modeling electric equipment type, and deposited Store up in unknown load characteristic parameter sample list;
Step 206: if being stored in unknown load characteristic parameter sample list of detecting do not model electric equipment class The sum accumulation of the load characteristic parameter sample of type reaches preset value k1, then step 207 is performed;Otherwise go to step 208;
Step 207: from all unknown load characteristic parameter sample accumulated, determine that difference does not models electric equipment The load characteristic parameter of type, and store the result in electric equipment load profile storehouse, simultaneously will with fixed not The load characteristic parameter sample that modeling electric equipment is relevant is deleted from unknown load characteristic parameter sample list;
Step 208: do not model the judgement of electric equipment type with whether existing about electric load inside of current time Whether result renewal is previous exists the judged result judging the moment not modeling electric equipment type about electric load inside; Update previous whether exist about electric load inside with the electric load characteristic of current time and do not model electric equipment The electric load characteristic judging the moment, go to step 202, circulation performs.
Further, for step 201, before presetting electric equipment load profile storehouse, in advance to electric power monitored Known electrical equipment device type in load, obtains corresponding load profile;And corresponding load profile is stored in electrical equipment In machine utilization property data base, as initial electric equipment load profile storehouse.
Preset electric equipment load profile storehouse to include in advance to the known electric equipment within electric load monitored Type, obtains corresponding load profile, and is stored in by corresponding load profile in electric equipment load profile storehouse, As initial electric equipment load profile storehouse;Parameter initialization, including presetting the load not modeling electric equipment type The preset value k of characteristic parameter total sample number1, the preset value k of the effective bunch of load characteristic sample size comprised2, do not model electrical equipment Equipment judges the design parameter in parameter and system used non-intrusive electrical load monitoring method.
Further, for step 204, according to the electric load corresponding with the electricity consumption status monitoring result of electric equipment Deviation size between feature assessment value and the electric load feature actual value collected is to judge the electric load of current time Whether inside exists does not models electric equipment type.
Further, also include that following whether existence does not models electric equipment type judgement method:
Step 1, determine the estimated value of electric load characteristic vector
It is one to one with electric equipment electricity consumption status monitoring result, can be according to electric equipment electricity condition Monitoring result and known electric equipment load characteristic parameter estimation and obtain, computational methods are shown below,
X L ^ ( t ) = Σ n = 1 N s n ( t ) · X n
In formula, snT () represents the electricity consumption state identification result of moment t n known electrical equipment device type, XnRepresent n The load characteristic Parameter Typical of known electrical equipment device type, the non-intrusive electrical load monitoring method used according to system Difference, can be use correlation method obtain electric equipment be in the electric current under different operating state and/or power features Representative value, wherein, n ∈ 1,2,3 ..., N}, N represent the total quantity of the internal known electrical equipment device type of electric load;
Step 2, set up judgement formulaIf inequality is set up, then show Moment t, electric load is internal exists the electric equipment type not modeled;
In formula, XL(t) represent moment t collect for electric equipment electricity consumption status monitoring electric load feature to The actual value of amount,Represent the estimation to the electric load characteristic vector of moment t of the electric equipment electricity consumption state monitoring method Value, | | | |pRepresenting the Lp-norm of vector, wherein p >=1, ε represents judgment threshold, it is judged that the optimum span of threshold epsilon is 5%~20%.
Further, for step 205, current to previous whether exist not about electric load inside including calculating The difference of the electric load characteristic parameter judging the moment of modeling electric equipment is special as the load not modeling electric equipment type Levy parameter sample.
Further, for step 206, about the load characteristic parameter total sample number not modeling electric equipment type Preset value k1, k1Value not less than 100.
Further, for step 207, including utilizing clustering method, the electrical equipment that do not models accumulated is set Standby load characteristic sample carries out cluster analysis, in cluster result, all comprises load characteristic sample size more than preset value k2A bunch respectively corresponding one do not model electric equipment type, all load characteristic samples comprised in each bunch are all by therewith Corresponding does not models what electric equipment type produced, and using bunch cluster centre special as the load not modeling electric equipment type The representative value levied;k2Value not less than 5.For clustering method, the present invention can use any prior art, such as, K-mean algorithm, k-central value algorithm, DBSCAN algorithm and cluster based on grid (grid-basedclustering) algorithm [Jiawei Han,Micheline Kamber,Jian Pei.Data Mining:Concepts and Techniques[M] .Elsevier, 2011] etc..
The present invention has the advantage that and provides the benefit that: propose a kind of non-intrusion type power load possessing self-learning function Lotus monitoring system, and propose a kind of non-intrusive electrical load monitoring method possessing self-learning function, utilize skill of the present invention Art achievement, non-intrusive electrical load monitoring technology system can detect not building of the internal existence of electric load monitored automatically Mould electric equipment, and automatically extract load characteristic parameter, finally in order to update non-intrusive electrical load monitoring technology system Electric equipment load profile storehouse, thus be no longer necessary to technical staff and safeguard by the way of artificial return visit user and update Electric equipment load profile storehouse;System monitoring is ensured when can increase and/or change electric equipment inside electric load newly Performance is unaffected, can be greatly saved again human cost, improves the operation effect of non-intrusive electrical load monitoring technology system Rate, therefore, it is possible to be greatly enhanced the practicality of non-intrusive electrical load monitoring technology;Supervise based on non-intrusive electrical load The big data of electric power of survey technology can greatly help the data assets that Utilities Electric Co.'s accumulation is excellent, upgrade its existing capability and industry Business, such as: Electric Power Network Planning and operational management, demand Side Management, customer service etc., and can expand company's function and business model Farmland;Meanwhile, it is capable to help power consumer using electricity wisely, the energy-saving and emission-reduction of the final promotion whole society.
Accompanying drawing explanation
Fig. 1 is the framework map of a kind of non-intrusive electrical load monitoring system possessing self-learning function of the present invention;
Fig. 2 is the flow chart of a kind of non-intrusive electrical load monitoring method possessing self-learning function of the present invention;
Fig. 3 is that the simulation of a kind of non-intrusive electrical load monitoring System and method for possessing self-learning function of the present invention is surveyed Examination circuit diagram (one);
Fig. 4 is that the simulation of a kind of non-intrusive electrical load monitoring System and method for possessing self-learning function of the present invention is surveyed Examination circuit diagram (two).
Detailed description of the invention
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described in detail: should be appreciated that preferred embodiment Only for the explanation present invention rather than in order to limit the scope of the invention.
As Figure 1-4, the present invention will be illustrated by the following examples
As it is shown in figure 1, a kind of non-intrusive electrical load monitoring system possessing self-learning function, use including electric load Electric data collecting module, electric load electrical feature acquisition module, the internal electric equipment electricity consumption state monitoring module of electric load, Electric equipment load profile storehouse, the traditional non-intrusive electrical load monitoring technology system of external interactive function module these five Outside contained functional module, also include not modeling electric equipment type load characteristic generation module.
Electric load electricity consumption data acquisition module, for gathering the terminal voltage of electric load power supply porch and total electricity Stream, specifically includes the strong voltage at by power import, big current analog signal is converted to electric load electrical feature acquisition module The light current pressure that can process and/or small area analysis analogue signal, and can obtain required for electric load electrical feature acquisition module Electric load electrical feature and with the sample frequency of satisfied requirement complete light current pressure and/or the numeral of small area analysis analogue signal Changing, the former can use voltage, current transformer to realize.
Electric load electrical feature acquisition module is for completing the data that voltage, current data filtering, noise reduction etc. are necessary On the basis of pretreatment, necessary data analysis and treatment technology method is used to obtain the internal electric equipment electricity consumption shape of electric load Electric load feature needed for state monitoring modular, such as, if desired obtains voltage, current harmonics feature, then can use Fourier Voltage, current signal are analyzed by conversion (FFT), if stress event feature need to be extracted, then detection of change-point method can be used [to open Learn new. detection of change-point problem latest developments summary [J]. Jianghan University's journal (natural science edition), 2012,40 (2): 18-24.] Detection load event from electric load electric power curve, then extract stress event associated loadings feature [Jian Liang, Ng,Simon K.K.,Kendall,G.,et al.Load Signature Study—Part I_Basic Concept, Structure,and Methodology[J].IEEE Transactions on Power Delivery,2010,25(2): 551–560]。
The internal electric equipment electricity consumption state monitoring module of electric load is for according to electric load electrical feature acquisition module The electric load feature provided, uses rational non-intrusive electrical load monitoring solving model and method for solving, determines electric power Inside load, every kind of electric equipment type uses electricity condition, including duty and/or electric power two aspect of electric equipment Content, described non-intrusive electrical load monitoring solving model and method for solving can be but not limited to [Patent No. CN200810053059.1 entitled " method for real time sorting non-intrusion type electric load "] [G.W.Hart.Nonintrusiveappliance load monitoring [J] .Proceedings of IEEE, 1992, 80 (12): 1870-1891.] [Steven B.Leeb, Steven R.Shaw, James L.Kirtley.Transient event detection in spectral envelope estimates for nonintrusive load The report such as monitoring [J] .IEEE Transactions on Power Delivery, 1995,10 (3): 1200-1210.] Solving model disclosed in road and method for solving.
Electric equipment load profile library module for storing and manage the load profile of electric equipment, including to Electric equipment electricity consumption state monitoring module provides the access interface in electric equipment load profile storehouse, and receives and store not The load profile not modeling electric equipment that modeling electric equipment type load characteristic generation module provides.
Externally interactive function module be used for realizing in non-intrusive electrical load monitoring technology system other functional modules with Data message interactive function necessary between the external world, include but not limited to monitoring result show, control command input with export and System Reports exports.
Do not model electric equipment type load characteristic generation module for according to electric equipment electricity consumption status monitoring result, from Move and detect that exist inside electric load monitored does not models electric equipment, and automatically obtain its load characteristic parameter sample, Finally according to the needs of the electric equipment electricity consumption state monitoring method that system is used, the load characteristic of electric equipment will not modeled Data export to electric equipment load profile library module and store.
As in figure 2 it is shown, a kind of non-intrusive electrical load monitoring method possessing self-learning function;
Step 201: parameter initialization, presets electric equipment load profile storehouse;
Step 202: gather electric load electricity consumption data, extracts the electric load characteristic of current time;
Step 203: utilize effective non-intrusive electrical load monitoring technology to carry out inside the electric load of current time Electric equipment electricity consumption status monitoring;
Step 204: according to monitoring result, it is judged that and record whether to exist inside current time electric load and do not model electrical equipment Device type, if adjacent two judge in the moment, with the presence of and the electric load in only one of which moment is internal does not models Electric equipment type;Then perform step 205;Otherwise go to step 208;
Step 205: do not model electric equipment type according to current to previous whether exist about electric load inside Judge the electric load characteristic in moment, extract the load characteristic parameter sample not modeling electric equipment type, and deposited Store up in unknown load characteristic parameter sample list;
Step 206: if being stored in unknown load characteristic parameter sample list of detecting do not model electric equipment class The sum accumulation of the load characteristic parameter sample of type reaches preset value k1, then step 207 is performed;Otherwise go to step 208;
Step 207: from all unknown load characteristic parameter sample accumulated, determine that difference does not models electric equipment The load characteristic parameter of type, and store the result in electric equipment load profile storehouse, simultaneously will with fixed not The load characteristic parameter sample that modeling electric equipment is relevant is deleted from unknown load characteristic parameter sample list;
Step 208: whether there is the judged result not modeling electric equipment type inside the electric load of current time Update the previous judged result judging the moment whether existing about electric load inside and not modeling electric equipment type;To work as Electric load characteristic renewal previous whether the existence about electric load inside in front moment does not models sentencing of electric equipment The electric load characteristic in disconnected moment, goes to step 202, and circulation performs.
Specifically, in step 201, carry out parameter initialization, when presetting electric equipment load profile storehouse, specifically wrap Include, take for the inventive method relates to relative parameters setting in technical method used by system (including innovative technology method of the present invention) Value, including the preset value k of load characteristic parameter total sample number1, the preset value of the load characteristic sample size that effective bunch is comprised k2, do not model electric equipment judgment threshold ε, the value of parameter p in formula (2), and the monitoring of used non-intrusive electrical load Design parameter in method, as entitled in Patent No. CN200810053059.1 " method for real time sorting non-intrusion type electric load " Middle primary voltage, the sample frequency of current signal, preset electric equipment load profile storehouse, including according to electric equipment electricity consumption The needs of state monitoring method, in advance to the known electrical equipment device type within electric load monitored, obtain corresponding load special Levy data and be stored in electric equipment load profile storehouse, according to the difference of non-intrusive electrical load monitoring method, institute The load characteristic used can be different, and as Patent No. CN200810053059.1 is entitled, " non-intrusive electrical load is real-time Decomposition method " in use current harmonics feature.In this article, corresponding with not modeling electric equipment type, it is known that electrical equipment Device type is also referred to as built mould electric equipment.
In step 204, the present invention estimates according to the electric load feature corresponding with the electricity consumption status monitoring result of electric equipment Deviation size between evaluation and the electric load feature actual value collected is to judge whether deposit in current time electric load Do not modeling electric equipment type;
First, the estimated value of electric load characteristic vector is determined
It is one_to_one corresponding with electric equipment electricity consumption status monitoring result, can supervise according to electric equipment electricity condition Surveying result and known electric equipment load characteristic parameter estimation and obtain, computational methods are shown below,
X L ^ ( t ) = Σ n = 1 N s n ( t ) · X n - - - ( 1 )
In formula, snT () represents the electricity consumption state identification result of moment t n known electrical equipment device type, XnRepresent n The load characteristic Parameter Typical of known electrical equipment device type, the non-intrusive electrical load monitoring method used according to system Difference, can be use correlation method obtain electric equipment be in the electric current under different operating state and/or power features Representative value, wherein, n ∈ 1,2,3 ..., N}, N represent the total quantity of the internal known electrical equipment device type of electric load;
If inequality shown in following formula (2) is set up, then showing at moment t, the internal electrical equipment not modeled that exists of electric load sets Standby type:
| | X L ( t ) - X L ^ ( t ) | | p ≥ ϵ · | | X L ( t ) | | p - - - ( 2 )
In formula, XL(t) represent moment t collect for electric equipment electricity consumption status monitoring electric load feature to The actual value of amount,Represent the estimation to the electric load characteristic vector of moment t of the electric equipment electricity consumption state monitoring method Value, | | | |pRepresenting the Lp-norm of vector, wherein p >=1, ε represents judgment threshold;
According to required, electric equipment detection sensitivity can not modeled for judgment threshold ε, technical staff or user Setting the value of this parameter, in the case of the setting of this value is less, system can compare " sensitive " to not modeling electric equipment so that The load characteristic sample that some known electric equipments produce is judged as being by not modeling what electric equipment produced, arranges in this value In the case of relatively big, system can compare " blunt " not modeling electric equipment, but, although there is omission not model electric equipment and bear The risk of lotus feature samples, but the load characteristic sample that known electric equipment produces is mistaken for being by not modeling electric equipment The probability produced can be substantially reduced.In engineering, it is judged that the optimum span of threshold epsilon is 5%~20%.
Due to different electric equipment electricity consumption state monitoring methods monitoring principle and or load characteristic type used can Can be different, therefore, the inventive method is to snThe span of (t) and XnRepresentative load characteristic type or load characteristic type Combination do not limit, with specific reference in non-intrusive electrical load monitoring technology system implementation process, system is actual to be used Electric equipment electricity consumption state monitoring method depending on, wherein, XnCan be the power features of electric load, current characteristic, harmonic wave Feature or combinations thereof.
For step 205, do not model electrical equipment set including calculating current to previous whether exist about electric load inside The difference of the standby electric load characteristic parameter judging the moment is as the load characteristic parameter sample not modeling electric equipment type; Such as, calculate the difference of electric load general power, the power features of electric equipment can not modeled, in like manner, calculate power load The difference of lotus total current harmonic characteristic, can not modeled the current harmonics feature of electric equipment.
For step 206, about the preset value k of the load characteristic parameter total sample number not modeling electric equipment type1, can With by technical staff according to the difference of application scenarios, or user is according to the different numerical value of the different set of application demand, value The less system that is favorably improved detects the real-time not modeling electric equipment, and value is favorably improved more greatly system detection and does not models The accuracy of electric equipment;In engineering, according to the calculating resource distribution of system, k1Value not less than 100.
For step 207, including utilizing clustering method, to the load characteristic not modeling electric equipment accumulated Sample carries out cluster analysis, in cluster result, all comprises load characteristic sample size more than preset value k2Bunch the most right Answering one not model electric equipment type, all load characteristic samples comprised in each bunch are all not modeled by corresponding Electric equipment produces, and using bunch cluster centre as the representative value of the load characteristic not modeling electric equipment type;Permissible By technical staff according to the difference of application scenarios, or user is according to the different numerical value of the different set of application demand, suitably Value contributes to guaranteeing the effectiveness not modeling electric equipment type that system is generated;In engineering, provide according to the calculating of system Source configures, and does not models the ageing of electric equipment detection, k for guarantee system as far as possible2Value not less than 5.
Based on principles above, it practice, existing non-intrusive electrical load is monitored system institute with method by present system The electric equipment electricity consumption state monitoring method used is not limited to them.Here, Patent No. is used herein CN200810053059.1 entitled " method for real time sorting non-intrusion type electric load " realizes the non-intrusion type electric power in step 203 Load monitoring, carrys out the effectiveness of the inventive method by experiment test.
First, the ultimate principle of method for real time sorting non-intrusion type electric load may be summarized as follows:
1, assume that electric load L monitored is internal containing N kind electric equipment, for n electric equipment, with its normal work Steady-state current harmonic characteristic when making, as imprinting signature, can be made and being expressed as:
in(t)=In,1·cos(w·t+θn,1)+···+In,k·cos(k·w·t+θn,k)+···(3)
In formula, inT () represents the instantaneous operating current of stable state of the n-th electric appliances equipment, n ∈ 1,2 ..., N}, N are the most whole Number;In,1Represent the fundametal compoment amplitude of described n electric equipment operating current;W represents that described n electric equipment works The angular frequency of the fundametal compoment of electric current;θn,1Represent the initial phase angle of the fundametal compoment of described n electric equipment operating current;In,k Represent the amplitude of kth order harmonic components in described n electric equipment operating current;θn,kRepresent kth subharmonic in operating current The initial phase angle of component;K is positive integer;Wherein, In,k=an,k×In,1, αn,kRepresent In,kAnd In,1Between proportionality coefficient.
After using perunit value, above formula (3) can be rewritten as:
i′n(t)=1 cos (w t+ θn,1)+···+αn,k·cos(k·w·t+θn,k)+···(4)
And in' (t) is referred to as the cell current of n electric equipment, the i.e. perunit value of its operating current fundamental voltage amplitude It it is electric current when 1.
2, characteristic vector I of n electric equipment current harmonics feature is obtainedn
So, application phasor describes, characteristic vector I of available expression n electric equipment current harmonics featuren For:
In=[1 ∠ θn,1,···,αn,k·∠θn,k,···]T (5)
According to above-mentioned definition, for the total current of electric load L monitored, can use the linear of this N kind electric equipment electric current Superposition carrys out approximate evaluation, thus has
i'L(t)=β1(t)·i1'(t)+β2(t)·i'2(t)···+βN(t)·i'N(t) (6)
In formula, i'LT () represents the unit total current of electric load L, characteristic of correspondence vector IL(t) as shown in formula (7), phase The definition of related parameter can be found in the definition of corresponding parameter in formula (3);i'1(t), i'2(t) and i'nT () represents the 1st, 2 and N respectively Planting the cell current of electric equipment, characteristic of correspondence vector is respectively I1, I2And IN;β1(t), β2(t) and βNT () represents respectively The current weights coefficient of 1,2 and N kind electric equipment, its span be [0 ,+∞), and define β (t)=[β1(t),β2 (t),…,βN(t)]T
IL(t)=[1 ∠ θL,1,···,αL,k·∠θL,k,···]T (7)
In formula, θL,1It it is the initial phase angle of the fundametal compoment of the steady state operating current of described electric load L;θL,kRepresent described electricity The initial phase angle of kth order harmonic components in the steady state operating current of power load L;K is positive integer;Wherein, αL,kWith αn,kIn like manner, represent Proportionality coefficient between fundametal compoment amplitude and its kth order harmonic components amplitude of the steady state operating current of described electric load L.
Application phasor approach describes, and above formula (6) can be to be expressed as form:
IL(t)=[I1,I2,···,IN]·β(t) (8)
3, the current weights coefficient of every kind of electric equipment is obtained
And then, can be by constraints β1(t), β2(t), and βN(t) ∈ [0 ,+∞) under solve shown in formula (9) excellent Change object function and obtain the current weights coefficient of every kind of electric equipment.
m i n β 1 ( t ) , β 2 ( t ) , ... , β n ( t ) ∈ [ 0 , + ∞ ) | | I L ( t ) - [ I 1 , I 2 , ... , I N ] · β ( t ) | | p - - - ( 9 )
In formula, | | | |pRepresent Lp norm, wherein p >=1.Calculated by formula (9) and also obtain every kind of electric equipment electric work The proportionality coefficient of rate, in conjunction with the total power value of electric load current time, it is possible to obtain every kind of electric equipment current time Electric power valuation.
It follows that first choose hair-dryer, water dispenser, electric kettle, television set, Sunny heater, electromagnetic oven and day The inventive method is tested by the test system that light modulation group is constituted, embodiment 1, as shown in Figure 3.In this test system, if Settled date, light modulation group was not for model electric equipment type, and other electric equipments are set as known electrical equipment device type.
Before starting test, according to described in step 201, set about the load characteristic parameter not modeling electric equipment type The preset value k of total sample number1Value is 50, sets the preset value k of the effective bunch of load characteristic sample size comprised2Value is 20, set and do not model the value of electric equipment judgment threshold ε as 10%, in formula (2), the value of parameter p is set to 2, if unknown load Characteristic parameter sample list is empty;On this basis, according to entitled " the non-intrusion type electric power of Patent No. CN200810053059.1 Load real-time decomposition method " principle, gather hair-dryer, water dispenser, electric kettle, television set, Sunny heater, electromagnetic oven These six kinds known electrical equipment device type steady-state current harmonic characteristics, preset electric equipment load profile storehouse.Here, 1 is only taken To 5 subharmonic features, according to practical situation, more higher hamonic wave feature can be taken.
For the core of context of methods, do not model electric equipment and automatically detect, in conjunction with above-mentioned Patent No. The know-why of CN200810053059.1 entitled " method for real time sorting non-intrusion type electric load ", according to basis formula (2) Suo Shi Invention does not models the ultimate principle that electric equipment judges, IL(t) and XLT () correspondence, i.e. electric load characteristic vector are taken as electric current humorous Wave characteristic vector, according to formula (1),WithCorrespondence, InWith XnCorrespondence, sn(t) and βnT () is corresponding.
In test process, use herein [Li Peng. non-intrusive electrical load decomposes and monitoring [D]. Tianjin: University Of Tianjin, 2009. the differential evolution algorithm recommended in] solves formula (9).As for clustering method, the present invention selects the k-means of classics Algorithm, specifically use report [Zhou Shibing, Xu Zhenyuan, Tang Xuqing. new k-mean algorithm preferable clustering number determines method [J]. meter Calculation machine engineering and application, 2010,46 (16): 27-31] algorithm disclosed in determines clusters number.
In a test system in the case of other known electric equipments contained normal start and stop at random, daylight lamp group experiences repeatedly After start and stop, solve that to obtain the power features Parameter Typical of daylight lamp group as follows:
Taking first five primary current harmonic characteristic, the current harmonics characteristic vector representative value obtained is:
[1∠-9.1°,0.08∠110.8°,0.21∠-139.7°,0,0.05∠97°]T (10)
Function according to not modeling electric equipment type load characteristic generation module describes and step 207, at the present embodiment In, do not model the electric equipment type load characteristic generation module current harmonics characteristic vector by the daylight lamp group shown in formula (10) Export in the electric equipment load profile library module of system.
By above-mentioned test, electric equipment load profile storehouse increase daylight lamp group load characteristic after by more Newly, at this moment daylight lamp group has been considered as known electric equipment.On this basis, do not change system parameter settings value, in test Increasing microwave oven in system to test as not modeling electric equipment type, as shown in Figure 4, embodiment 2 is in a test system In the case of other known electric equipments contained normal start and stop at random, after microwave oven experiences repeatedly start and stop, solve and obtain microwave oven Power features Parameter Typical as follows:
Taking first five primary current harmonic characteristic, the characteristic vector representative value of the current waveform obtained is:
[1∠1.7°,0.07∠5.2°,0.43∠-121.2°,0.02∠48.7°,0.13∠-44.9°]T (11)
Ibid, describe and step 207, in this reality according to the function not modeling electric equipment type load characteristic generation module Execute in example, do not model electric equipment type load characteristic generation module by the current harmonics feature of the microwave oven shown in formula (11) to Amount exports in the electric equipment load profile library module of system.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, it is not intended to limit;To the greatest extent The present invention has been described in detail by pipe with reference to foregoing embodiments, it will be understood by those within the art that: it depends on So the technical scheme described in foregoing embodiments can be modified, or the most some or all of technical characteristic is entered Row equivalent;And these amendments or replacement, do not make the essence of appropriate technical solution depart from various embodiments of the present invention technology The scope of scheme.

Claims (9)

1. possesses a non-intrusive electrical load monitoring system for self-learning function, including electric load electricity consumption data acquisition module Block, electric load electrical feature acquisition module, electric load internal electric equipment electricity consumption state monitoring module, electric equipment load Characteristic library module, external interactive function module, it is characterised in that: also include not modeling electric equipment type load characteristic raw Become module;
Described electric load electricity consumption data acquisition module, for gathering the terminal voltage of electric load power supply porch with total Electric current;
Described electric load electrical feature acquisition module, the voltage that electric load electricity consumption data collecting module collected is arrived, electricity The data such as flow data is filtered, noise reduction, smooth process, and then obtain the internal electric equipment electricity consumption status monitoring mould of electric load Electric load feature needed for block;
The internal electric equipment electricity consumption state monitoring module of described electric load is for obtaining mould according to electric load electrical feature The electric load feature that block provides, uses rational non-intrusive electrical load monitoring solving model and method for solving, determines electricity Inside power load, every kind of electric equipment type uses electricity condition, including duty and/or electric power two side of electric equipment Face content;
Described electric equipment load profile library module is used for storing and managing the load profile of electric equipment, including The access interface in electric equipment load profile storehouse is provided to the internal electric equipment electricity consumption state monitoring module of electric load, with And receive and store the load characteristic not modeling electric equipment that the offer of electric equipment type load characteristic generation module is not provided Data;
Described external interactive function module is used for realizing other functional modules in non-intrusive electrical load monitoring technology system And data message interactive function necessary between the external world, include but not limited to monitoring result show, control command input with export, And System Reports output;
The described electric equipment type load characteristic generation module that do not models for according to electric equipment electricity consumption status monitoring result, That automatically detects the internal existence of electric load monitored does not models electric equipment, and automatically obtains its load characteristic parameter sample; Further, described does not models electric equipment type load characteristic generation module, uses according to the electric equipment that system is used The needs of electricity condition monitoring method, export the load profile not modeling electric equipment to electric equipment load profile Library module is also preserved by described electric equipment load profile library module.
A kind of non-intrusive electrical load monitoring system possessing self-learning function the most according to claim 1, its feature It is: described electric load electricity consumption data acquisition module, gathers the strong voltage at power import, big current analog signal, and It is converted into light current pressure and/or small area analysis analogue signal that electric load electrical feature acquisition module can process, then will Acquired light current pressure and/or small area analysis analog signal digital, extract required for electric load with electrical feature acquisition module Electric load electrical feature.
3. the non-intrusive electrical load monitoring method possessing self-learning function, it is characterised in that: it is applied to claim In a kind of non-intrusive electrical load monitoring system possessing self-learning function of 1-2, comprise the following steps:
Step 201: parameter initialization, presets electric equipment load profile storehouse;
Step 202: gather electric load electricity consumption data, extracts the electric load characteristic of current time;
Step 203: utilize effective non-intrusive electrical load monitoring technology to carry out the internal electrical equipment of electric load of current time Equipment electricity consumption status monitoring;
Step 204: according to monitoring result, it is judged that and record whether to exist inside current time electric load and do not model electric equipment Type, if adjacent two judge in the moment, with the presence of and the electric load in only one of which moment is internal does not models electrical equipment Device type;Then perform step 205;Otherwise go to step 208;
Step 205: do not model the judgement of electric equipment type according to current to previous whether exist about electric load inside The electric load characteristic in moment, extracts the load characteristic parameter sample not modeling electric equipment type, and stores it in In unknown load characteristic parameter sample list;
Step 206: if being stored in unknown load characteristic parameter sample list of detecting do not model electric equipment type The sum accumulation of load characteristic parameter sample reaches preset value k1, then step 207 is performed;Otherwise go to step 208;
Step 207: from all unknown load characteristic parameter sample accumulated, determine that difference does not models electric equipment type Load characteristic parameter, and store the result in electric equipment load profile storehouse, will not model with fixed simultaneously The load characteristic parameter sample that electric equipment is relevant is deleted from unknown load characteristic parameter sample list;
Step 208: do not model the judged result of electric equipment type with whether existing about electric load inside of current time Update the previous judged result judging the moment whether existing about electric load inside and not modeling electric equipment type;To work as Electric load characteristic renewal previous whether the existence about electric load inside in front moment does not models sentencing of electric equipment The electric load characteristic in disconnected moment, goes to step 202, and circulation performs.
A kind of non-intrusive electrical load monitoring method possessing self-learning function the most according to claim 3, its feature It is: for step 201, presets electric equipment load profile storehouse and include known within electric load monitored in advance Electric equipment type, obtains corresponding load profile, and corresponding load profile is stored in electric equipment load characteristic In data base, as initial electric equipment load profile storehouse;Parameter initialization, does not models electric equipment class including presetting The preset value k of the load characteristic parameter total sample number of type1, the load characteristic sample not modeling electric equipment accumulated is entered Row cluster analysis, in cluster result, corresponding with not modeling electric equipment type bunch is considered as effective bunch, and effective bunch is comprised The preset value k of load characteristic sample size2, do not model electric equipment type judge parameter and system used non-intrusion type electricity Design parameter in power load monitoring method.
A kind of non-intrusive electrical load monitoring method possessing self-learning function the most according to claim 3, its feature It is: for step 204, according to the electric load feature assessment value corresponding with the electricity consumption status monitoring result of electric equipment with adopt Collect to electric load feature actual value between deviation size judge whether exist not inside the electric load of current time Modeling electric equipment type.
A kind of non-intrusive electrical load monitoring method possessing self-learning function the most according to claim 5, its feature It is: also include below in relation to whether there is the determination methods not modeling electric equipment type:
Step 1, determine the estimated value of electric load characteristic vector
It is one to one with electric equipment electricity consumption status monitoring result, can be according to electric equipment electricity consumption status monitoring Result and known electric equipment load characteristic parameter estimation and obtain, computational methods are shown below,
X L ^ ( t ) = Σ n = 1 N s n ( t ) · X n
In formula, snT () represents the electricity consumption state identification result of moment t n known electrical equipment device type, XnRepresent that n is known The load characteristic Parameter Typical of electric equipment type, wherein, n ∈ 1,2,3 ..., N}, N represent the internal known electric of electric load The total quantity of device device type;
Step 2, set up judgement formulaIf inequality is set up, then show in the moment T, electric load is internal exists the electric equipment type not modeled;
In formula, XLT () represents the electric load characteristic vector for electric equipment electricity consumption status monitoring that collects at moment t Actual value,Represent the electric equipment electricity consumption state monitoring method estimated value to the electric load characteristic vector of moment t, | |·||pRepresent vector Lp-norm, wherein p >=1, ε represents judgment threshold, it is judged that the optimum span of threshold epsilon be 5%~ 20%.
A kind of non-intrusive electrical load monitoring method possessing self-learning function the most according to claim 3, its feature It is: for step 205, does not models electric equipment including calculating current to previous whether exist about electric load inside Judge that the difference of electric load characteristic parameter in moment is as the load characteristic parameter sample not modeling electric equipment type.
A kind of non-intrusive electrical load monitoring method possessing self-learning function the most according to claim 3, its feature It is: for step 206, about the preset value k of the load characteristic parameter total sample number not modeling electric equipment type1, k1Take Value is not less than 100.
A kind of non-intrusive electrical load monitoring method possessing self-learning function the most according to claim 3, its feature It is: for step 207, including utilizing clustering method, to the load characteristic sample not modeling electric equipment accumulated Originally carry out cluster analysis, in cluster result, all comprise load characteristic sample size more than preset value k2Bunch respectively corresponding One does not models electric equipment type, and all load characteristic samples comprised in each bunch are not modeled electrical equipment by corresponding Device type produces, and using bunch cluster centre as the representative value of the load characteristic not modeling electric equipment type;k2's Value is not less than 5.
CN201610530542.9A 2016-07-07 2016-07-07 A kind of non-intrusive electrical load monitoring System and method for having self-learning function Active CN106093652B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610530542.9A CN106093652B (en) 2016-07-07 2016-07-07 A kind of non-intrusive electrical load monitoring System and method for having self-learning function

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610530542.9A CN106093652B (en) 2016-07-07 2016-07-07 A kind of non-intrusive electrical load monitoring System and method for having self-learning function

Publications (2)

Publication Number Publication Date
CN106093652A true CN106093652A (en) 2016-11-09
CN106093652B CN106093652B (en) 2019-03-29

Family

ID=57213031

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610530542.9A Active CN106093652B (en) 2016-07-07 2016-07-07 A kind of non-intrusive electrical load monitoring System and method for having self-learning function

Country Status (1)

Country Link
CN (1) CN106093652B (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106762594A (en) * 2017-01-12 2017-05-31 威胜集团有限公司 Compressor apparatus start method of real-time
CN106872824A (en) * 2017-02-15 2017-06-20 宁波华创锐科智能科技有限公司 A kind of network load appliance type identification and the method and its device of different electrical equipment electricity statistics
CN106936129A (en) * 2017-03-23 2017-07-07 东北大学 Electric load discrimination method based on multi-feature fusion and system
CN108399221A (en) * 2018-02-11 2018-08-14 山东建筑大学 Indoor electric equipment classifying identification method and system based on big data association analysis
CN108537385A (en) * 2018-04-12 2018-09-14 广东电网有限责任公司 A kind of non-intrusion type residential electricity consumption load recognition methods
CN108594041A (en) * 2018-04-23 2018-09-28 中国计量大学 A kind of detection platform for non-intrusion type household electric load monitoring device
CN108693417A (en) * 2018-03-28 2018-10-23 淮阴师范学院 A kind of intelligent grid non-intrusion type resident load observation circuit and system
CN108733661A (en) * 2017-04-13 2018-11-02 深圳点亮新能源技术有限公司 A kind of online load characteristic library maintaining method towards non-intruding monitor
CN109001528A (en) * 2018-06-14 2018-12-14 国网江苏省电力有限公司电力科学研究院 A kind of non-intrusion type metering separate acquisition system
CN109245099A (en) * 2018-10-29 2019-01-18 南方电网科学研究院有限责任公司 A kind of electric load discrimination method, device, equipment and readable storage medium storing program for executing
CN109765443A (en) * 2019-01-17 2019-05-17 创炘源智能科技(上海)有限公司 Detect the device and method of the electric appliance load on power supply line
CN109870600A (en) * 2019-04-04 2019-06-11 江苏林洋能源股份有限公司 A kind of non-intrusion type load discrimination method and intelligent electric meter with self-learning capability
WO2019109582A1 (en) * 2017-12-08 2019-06-13 亿可能源科技(上海)有限公司 Non-intrusive energy consumption detection method and system
CN109946543A (en) * 2019-03-28 2019-06-28 西南交通大学 V-I figure sample data set screening technique for non-intrusion type load monitoring
CN110188771A (en) * 2019-05-17 2019-08-30 湖南大学 Non-intrusive electrical load feature extraction, recognition methods, system and medium based on image procossing

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5483153A (en) * 1994-03-24 1996-01-09 Massachusetts Institute Of Technology Transient event detector for use in nonintrusive load monitoring systems
CN101038327A (en) * 2007-04-03 2007-09-19 天津大学 Method for recognizing dynamic parameter of electrical system non-invasive induction motor dynamic parameter
CN101282040A (en) * 2008-05-09 2008-10-08 天津大学 Method for real time sorting non-intrusion type electric load
CN103675378A (en) * 2013-09-23 2014-03-26 东北电力大学 A non-intruding-type household-used electric load decomposition method and an apparatus
CN104483575A (en) * 2014-12-22 2015-04-01 天津求实智源科技有限公司 Self-adaptive load event detection method for noninvasive power monitoring
CN105429135A (en) * 2015-12-08 2016-03-23 河南许继仪表有限公司 Distinguishing and decision-making method and system for noninvasive power load decomposition

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5483153A (en) * 1994-03-24 1996-01-09 Massachusetts Institute Of Technology Transient event detector for use in nonintrusive load monitoring systems
CN101038327A (en) * 2007-04-03 2007-09-19 天津大学 Method for recognizing dynamic parameter of electrical system non-invasive induction motor dynamic parameter
CN101282040A (en) * 2008-05-09 2008-10-08 天津大学 Method for real time sorting non-intrusion type electric load
CN103675378A (en) * 2013-09-23 2014-03-26 东北电力大学 A non-intruding-type household-used electric load decomposition method and an apparatus
CN104483575A (en) * 2014-12-22 2015-04-01 天津求实智源科技有限公司 Self-adaptive load event detection method for noninvasive power monitoring
CN105429135A (en) * 2015-12-08 2016-03-23 河南许继仪表有限公司 Distinguishing and decision-making method and system for noninvasive power load decomposition

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
GEORGE W. HART: "Nonintrusive Appliance Load Monitoring", 《PROCEEDINGS OF IEEE》 *
佘贻鑫 等: "非侵入式居民电力负荷监测与分解技术", 《南方电网技术》 *

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106762594A (en) * 2017-01-12 2017-05-31 威胜集团有限公司 Compressor apparatus start method of real-time
CN106762594B (en) * 2017-01-12 2018-09-14 威胜集团有限公司 Compressor apparatus starts method of real-time
CN106872824A (en) * 2017-02-15 2017-06-20 宁波华创锐科智能科技有限公司 A kind of network load appliance type identification and the method and its device of different electrical equipment electricity statistics
CN106936129B (en) * 2017-03-23 2020-04-24 东北大学 Power load identification method and system based on multi-feature fusion
CN106936129A (en) * 2017-03-23 2017-07-07 东北大学 Electric load discrimination method based on multi-feature fusion and system
CN108733661A (en) * 2017-04-13 2018-11-02 深圳点亮新能源技术有限公司 A kind of online load characteristic library maintaining method towards non-intruding monitor
WO2019109582A1 (en) * 2017-12-08 2019-06-13 亿可能源科技(上海)有限公司 Non-intrusive energy consumption detection method and system
CN108399221A (en) * 2018-02-11 2018-08-14 山东建筑大学 Indoor electric equipment classifying identification method and system based on big data association analysis
CN108693417A (en) * 2018-03-28 2018-10-23 淮阴师范学院 A kind of intelligent grid non-intrusion type resident load observation circuit and system
CN108537385A (en) * 2018-04-12 2018-09-14 广东电网有限责任公司 A kind of non-intrusion type residential electricity consumption load recognition methods
CN108594041B (en) * 2018-04-23 2020-06-16 中国计量大学 Detection platform for non-invasive household power load monitoring device
CN108594041A (en) * 2018-04-23 2018-09-28 中国计量大学 A kind of detection platform for non-intrusion type household electric load monitoring device
CN109001528A (en) * 2018-06-14 2018-12-14 国网江苏省电力有限公司电力科学研究院 A kind of non-intrusion type metering separate acquisition system
CN109001528B (en) * 2018-06-14 2020-10-16 国网江苏省电力有限公司电力科学研究院 Non-invasive subentry measurement acquisition system
CN109245099A (en) * 2018-10-29 2019-01-18 南方电网科学研究院有限责任公司 A kind of electric load discrimination method, device, equipment and readable storage medium storing program for executing
CN109765443A (en) * 2019-01-17 2019-05-17 创炘源智能科技(上海)有限公司 Detect the device and method of the electric appliance load on power supply line
CN109946543A (en) * 2019-03-28 2019-06-28 西南交通大学 V-I figure sample data set screening technique for non-intrusion type load monitoring
CN109946543B (en) * 2019-03-28 2020-04-21 西南交通大学 V-I pattern sample data set screening method for non-invasive load monitoring
CN109870600A (en) * 2019-04-04 2019-06-11 江苏林洋能源股份有限公司 A kind of non-intrusion type load discrimination method and intelligent electric meter with self-learning capability
CN110188771A (en) * 2019-05-17 2019-08-30 湖南大学 Non-intrusive electrical load feature extraction, recognition methods, system and medium based on image procossing

Also Published As

Publication number Publication date
CN106093652B (en) 2019-03-29

Similar Documents

Publication Publication Date Title
Dileep A survey on smart grid technologies and applications
Reddy et al. A review of Integration, Control, Communication and Metering (ICCM) of renewable energy based smart grid
Bayindir et al. Smart grid technologies and applications
Von Meier et al. Micro-synchrophasors for distribution systems
US10833532B2 (en) Method and system for managing a power grid
Giannakis et al. Monitoring and optimization for power grids: A signal processing perspective
Barai et al. Smart metering and functionalities of smart meters in smart grid-a review
Zheng et al. Smart meters in smart grid: An overview
CN103872782B (en) A kind of power quality data integrated service system
Bhatt et al. An instrumentation engineer’s review on smart grid: Critical applications and parameters
CN102928809B (en) Electric energy metering device remote monitoring diagnostic system and working method thereof
JP5727063B1 (en) Energy management apparatus, energy management system, energy management method and program
Gungor et al. A survey on smart grid potential applications and communication requirements
CN106351793B (en) System and method for improving wind power generation
US7693670B2 (en) Cognitive electric power meter
CN103597707B (en) There is the distributed intelligence framework of the most reversely/forward cloud
CN102184209B (en) Simulation data accessing method based on power grid CIM (Common Information Model) interface
CN102510127B (en) Method for unifying models of on-line monitored first and secondary equipment of power grid
Huang et al. Data quality issues for synchrophasor applications Part I: a review
Sodhi et al. A simple scheme for wide area detection of impending voltage instability
Della Giustina et al. Electrical distribution system state estimation: measurement issues and challenges
CN203117771U (en) Building energy consumption intelligent monitoring and management system
US9189822B2 (en) Process, device and system for mapping transformers to meters and locating non-technical line losses
US20130066479A1 (en) Energy consumption disaggregation system
US9817045B2 (en) Methods and system for nonintrusive load monitoring

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
GR01 Patent grant